Claude-Skills-collection

In the author's own words, from each skill's SKILL.md — showing the first 29 of 138 files.

• agent-instructions

  Use when writing project instructions for a coding agent (CLAUDE.md, AGENTS.md, or equivalent). Covers what belongs in them, what does not, structure, and keeping them accurate as the project changes. Trigger on "write a claude.md for this repo", "set up agents.md", "the agent keeps running the wrong test command". Do not use for rules that must hold every time — see the hooks skill; for notes th…

  skills/agent-tooling/agent-instructions/SKILL.md on GitHub (opens in a new tab)

• agent-memory

  Use when an agent needs state that survives a session or a context compaction. Covers what to persist, file-based memory, structuring notes for retrieval, and preventing memory from becoming stale. Trigger on "agent forgets everything between sessions", "agent keeps retrying the same failed approach". Do not use for trimming the current context window — see the context-engineering skill; for huma…

  skills/agent-tooling/agent-memory/SKILL.md on GitHub (opens in a new tab)

• hooks

  Use when automating agent behavior with lifecycle hooks. Covers hook events, deterministic enforcement of rules the model should not be trusted to remember, and avoiding hooks that make an agent unusable. Trigger on "run prettier after every edit", "block rm -rf", "claude keeps forgetting to run tests". Do not use for guidance the agent should usually follow — see the agent-instructions skill; fo…

  skills/agent-tooling/hooks/SKILL.md on GitHub (opens in a new tab)

• plugin-development

  Use when packaging skills, commands, hooks, and MCP servers into a distributable plugin. Covers manifest structure, bundling, versioning, testing, and distribution through a marketplace. Trigger on "package my skills as a plugin", "publish to a plugin marketplace", "share our commands with the team", "bump the plugin version". Do not use for writing one skill — see the skill-authoring skill; for…

  skills/agent-tooling/plugin-development/SKILL.md on GitHub (opens in a new tab)

• skill-authoring

  Use when writing a new skill for an AI agent. Covers scoping, description writing for reliable triggering, progressive disclosure, and the difference between a skill and a prompt. Trigger on "write a skill for", "turn this prompt into a skill", "create a skill.md", "how do i write a skill description". Do not use for auditing an existing skill or library — see the skill-review skill; for workflow…

  skills/agent-tooling/skill-authoring/SKILL.md on GitHub (opens in a new tab)

• skill-review

  Use when reviewing or improving an existing agent skill. Covers triggering accuracy, content quality, redundancy with the base model, and measuring whether the skill actually changes behavior. Trigger on "my skill never triggers", "review this skill", "these two skills overlap", "audit our skill library". Do not use for writing a skill from scratch — see the skill-authoring skill.

  skills/agent-tooling/skill-review/SKILL.md on GitHub (opens in a new tab)

• slash-commands

  Use when creating reusable slash commands for an agent. Covers when a command beats a skill, argument handling, composing tool calls, and writing commands that are worth typing. Trigger on "make a slash command for", "i keep typing the same prompt", "pass arguments to my command". Do not use for capabilities the model should load on its own — see the skill-authoring skill; for enforcement on ever…

  skills/agent-tooling/slash-commands/SKILL.md on GitHub (opens in a new tab)

• subagents

  Use when delegating work to a separate agent with its own context. Covers when delegation pays off, designing a subagent's scope and prompt, parallel fan-out, and the cost of a cold start. Trigger on "spin up a subagent for this", "run these searches in parallel", "the search results are flooding my context", "have a fresh agent verify this". Do not use for building a standalone tool-using agent…

  skills/agent-tooling/subagents/SKILL.md on GitHub (opens in a new tab)

• agent-design

  Use when building an LLM agent that uses tools over multiple steps. Covers tool design, the agent loop, error recovery, termination, human checkpoints, and knowing when an agent is the wrong architecture. Trigger on "my agent keeps looping", "agent calls the wrong tool", "build an agent that can use our api". Do not use for delegating work to a subagent — see the subagents skill; for building the…

  skills/ai/agent-design/SKILL.md on GitHub (opens in a new tab)

• context-engineering

  Use when managing what an LLM sees. Covers context-window budgeting, retrieval and compaction, memory across turns, tool-result pruning, and the failure modes that come from too much context rather than too little. Trigger on "model gets worse as the conversation gets longer", "context window keeps filling up". Do not use for state that persists across sessions — see the agent-memory skill; for r…

  skills/ai/context-engineering/SKILL.md on GitHub (opens in a new tab)

• fine-tuning

  Use when considering fine-tuning a model. Covers when fine-tuning beats prompting or RAG, dataset construction, LoRA and full fine-tuning, evaluation, and the failure modes that waste the effort. Trigger on "should we fine-tune or just prompt", "fine-tune a small model to replace the big one", "prepare a dataset for lora". Do not use for giving the model fresh or private knowledge — see the rag s…

  skills/ai/fine-tuning/SKILL.md on GitHub (opens in a new tab)

• llm-cost-optimization

  Use when an LLM feature costs too much. Covers prompt caching, context reduction, model routing, batching, output limits, and finding where the tokens actually go. Trigger on "our openai bill is too high", "llm costs are out of control", "where are all these tokens going", "set up prompt caching". Do not use for cloud infrastructure spend — see the aws-cost-optimization skill; for choosing a chea…

  skills/ai/llm-cost-optimization/SKILL.md on GitHub (opens in a new tab)

• llm-evaluation

  Use when measuring the quality of an LLM feature. Covers building an evaluation set, choosing metrics, LLM-as-judge and its pitfalls, regression testing prompts, and evaluating in production. Trigger on "did my prompt change make it better", "build an eval set", "can i use an llm as a judge", "users say the answers got worse". Do not use for rewriting the prompt itself — see the prompt-engineerin…

  skills/ai/llm-evaluation/SKILL.md on GitHub (opens in a new tab)

• llm-integration

  Use when integrating an LLM API into an application. Covers streaming, retries and rate limits, timeouts, caching, fallback across providers, and the production concerns that a tutorial integration ignores. Trigger on "add an llm to our app", "getting 429 rate limit errors from the api", "stream the response to the frontend". Do not use for reducing token spend — see the llm-cost-optimization ski…

  skills/ai/llm-integration/SKILL.md on GitHub (opens in a new tab)

• mcp-server

  Use when building a Model Context Protocol server. Covers tool, resource, and prompt design, transport choice, authentication, error handling, and testing an MCP server against a real client. Trigger on "build an mcp server", "expose our api to claude", "the model keeps calling my mcp tool wrong". Do not use for packaging the server into a distributable plugin — see the plugin-development skill;…

  skills/ai/mcp-server/SKILL.md on GitHub (opens in a new tab)

• ml-pipeline

  Use when building or operating a machine learning pipeline. Covers feature engineering, training reproducibility, train/serve skew, deployment, monitoring for drift, and retraining. Trigger on "model worked offline but fails in production", "training runs aren't reproducible", "detect data drift", "set up retraining". Do not use for adapting an LLM with LoRA or fine-tuning — see the fine-tuning s…

  skills/ai/ml-pipeline/SKILL.md on GitHub (opens in a new tab)

• model-selection

  Use when choosing which LLM to use for a task. Covers matching capability to task, cost and latency trade-offs, routing between models, benchmark skepticism, and evaluating on your own data. Trigger on "which model should i use for this", "is the new model worth switching to", "route easy requests to a cheaper model". Do not use for building the evaluation set itself — see the llm-evaluation skil…

  skills/ai/model-selection/SKILL.md on GitHub (opens in a new tab)

• prompt-engineering

  Use when writing or improving prompts for a language model. Covers instruction structure, examples, reasoning elicitation, output formatting, and systematically diagnosing why a prompt fails. Trigger on "improve this prompt", "the model ignores my instructions", "prompt works sometimes and fails randomly". Do not use for guaranteeing schema-valid JSON — see the structured-output skill; for measur…

  skills/ai/prompt-engineering/SKILL.md on GitHub (opens in a new tab)

• rag

  Use when building retrieval-augmented generation. Covers chunking, embedding and hybrid search, reranking, grounding and citation, and diagnosing whether a bad answer is a retrieval failure or a generation failure. Trigger on "our rag keeps hallucinating", "chat with our docs", "retrieval returns the wrong documents". Do not use for managing context in a long conversation — see the context-engine…

  skills/ai/rag/SKILL.md on GitHub (opens in a new tab)

• structured-output

  Use when an LLM must return machine-readable data. Covers schema design for models, native structured-output modes, validation and repair, and extraction that survives contact with messy input. Trigger on "llm returns invalid json", "extract fields from these emails", "classify tickets into fixed categories". Do not use for scraping web pages — see the web-data-extraction skill; for general promp…

  skills/ai/structured-output/SKILL.md on GitHub (opens in a new tab)

• api-design

  Use when designing or reviewing an HTTP API. Covers resource modeling, status codes, pagination, idempotency, versioning, error formats, and the contract details that break clients when you get them wrong. Trigger on "design the endpoints for this", "what status code should this return", "how should we paginate this api", "review our openapi spec". Do not use for GraphQL schemas — see the graphql…

  skills/backend/api-design/SKILL.md on GitHub (opens in a new tab)

• background-jobs

  Use when designing asynchronous job processing. Covers queue selection, idempotency, retry and backoff policy, scheduling, poison messages, and observability for work that happens outside the request. Trigger on "move this to a background job", "emails are being sent twice", "the queue is stuck", "retry failed jobs with backoff". Do not use for event schemas other teams consume — see the event-dr…

  skills/backend/background-jobs/SKILL.md on GitHub (opens in a new tab)

• caching

  Use when adding or debugging a cache. Covers cache placement, invalidation strategies, stampede protection, TTL selection, and the consistency you are trading away. Trigger on "add redis caching", "users are seeing stale data", "cache stampede after expiry", "should we cache this". Do not use for browser caching headers and page load — see the web-performance skill; for a query that is slow at th…

  skills/backend/caching/SKILL.md on GitHub (opens in a new tab)

• django

  Use when building Django applications. Covers ORM query performance, model design, migrations, Django REST Framework, security defaults, and testing. Trigger on "django view is slow", "too many queries from the orm", "add a drf endpoint", "migration on a big table". Do not use for API contract decisions independent of Django — see the api-design skill.

  skills/backend/django/SKILL.md on GitHub (opens in a new tab)

• event-driven-architecture

  Use when designing systems around events and message queues. Covers event schema design, delivery guarantees, idempotent consumers, ordering, dead-letter handling, and event sourcing. Trigger on "should we use kafka", "messages are processed twice", "consumer is stuck", "design the event schema". Do not use for a simple task queue of background work — see the background-jobs skill; for whether to…

  skills/backend/event-driven-architecture/SKILL.md on GitHub (opens in a new tab)

• fastapi

  Use when building APIs with FastAPI. Covers dependency injection, Pydantic v2 validation, async database access, authentication, background tasks, and testing. Trigger on "fastapi endpoint is slow under load", "set up depends for the db session", "pydantic v2 validation error", "test my fastapi app". Do not use for API contract decisions like pagination or versioning — see the api-design skill.

  skills/backend/fastapi/SKILL.md on GitHub (opens in a new tab)

• graphql

  Use when designing or operating a GraphQL API. Covers schema design, resolver performance and DataLoader batching, query cost limiting, error handling, and federation. Trigger on "graphql query is slow", "n+1 in my resolvers", "set up dataloader", "limit query depth on our graphql endpoint". Do not use for REST endpoint design — see the api-design skill.

  skills/backend/graphql/SKILL.md on GitHub (opens in a new tab)

• microservices

  Use when decomposing a system into services, or deciding whether to. Covers service boundaries, inter-service communication, distributed data, saga patterns, and the operational cost of the network. Trigger on "should we split the monolith", "extract this into a service", "our services are too coupled". Do not use for broker and event design — see the event-driven-architecture skill; for pre-buil…

  skills/backend/microservices/SKILL.md on GitHub (opens in a new tab)

• nestjs

  Use when building NestJS services. Covers module structure, providers and scopes, validation pipes, guards and interceptors, TypeORM/Prisma integration, and testing. Trigger on "nest can't resolve dependencies", "add a guard for auth", "validation pipe not working", "test my nest module". Do not use for API contract decisions like pagination or versioning — see the api-design skill.

  skills/backend/nestjs/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• oh-my-openagentby code-yeongyu OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering. 70.7k stars · 25 skills
• AI-Research-SKILLsby Orchestra-Research Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gem… 14.3k stars · 30 skills
• cavemanby JuliusBrussee 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman. 118k stars · 22 skills
• OpenMontageby calesthio World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge… 76.5k stars · 30 skills
• scientific-agent-skillsby K-Dense-AI Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use va… 56.1k stars · 30 skills
• CowAgentby zhayujie Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent,… 47.8k stars · 3 skills